No Cover Image

Conference Paper/Proceeding/Abstract 1210 views 299 downloads

Graph Convolutional Neural Network

Mike Edwards, Xianghua Xie Orcid Logo

British Machine Vision Conference

Swansea University Author: Xianghua Xie Orcid Logo

Abstract

The benefit of localized features within the regular domain has given rise to the use of Convolutional Neural Networks (CNNs) in machine learning, with great proficiency in the image classification. The use of CNNs becomes problematic within the irregular spatial domain due to design and convolution...

Full description

Published in: British Machine Vision Conference
Published: 2016
URI: https://cronfa.swan.ac.uk/Record/cronfa32103
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2017-02-25T05:04:37Z
last_indexed 2018-02-09T05:19:40Z
id cronfa32103
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2017-03-23T12:27:29.0917621</datestamp><bib-version>v2</bib-version><id>32103</id><entry>2017-02-24</entry><title>Graph Convolutional Neural Network</title><swanseaauthors><author><sid>b334d40963c7a2f435f06d2c26c74e11</sid><ORCID>0000-0002-2701-8660</ORCID><firstname>Xianghua</firstname><surname>Xie</surname><name>Xianghua Xie</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2017-02-24</date><deptcode>SCS</deptcode><abstract>The benefit of localized features within the regular domain has given rise to the use of Convolutional Neural Networks (CNNs) in machine learning, with great proficiency in the image classification. The use of CNNs becomes problematic within the irregular spatial domain due to design and convolution of a kernel filter being non-trivial. One so- lution to this problem is to utilize graph signal processing techniques and the convolution theorem to perform convolutions on the graph of the irregular domain to obtain feature map responses to learnt filters. We propose graph convolution and pooling operators analogous to those in the regular domain. We also provide gradient calculations on the input data and spectral filters, which allow for the deep learning of an irregular spatial do- main problem. Signal filters take the form of spectral multipliers, applying convolution in the graph spectral domain. Applying smooth multipliers results in localized convo- lutions in the spatial domain, with smoother multipliers providing sharper feature maps. Algebraic Multigrid is presented as a graph pooling method, reducing the resolution of the graph through agglomeration of nodes between layers of the network. Evaluation of performance on the MNIST digit classification problem in both the regular and irregu- lar domain is presented, with comparison drawn to standard CNN. The proposed graph CNN provides a deep learning method for the irregular domains present in the machine learning community, obtaining 94.23% on the regular grid, and 94.96% on a spatially irregular subsampled MNIST.</abstract><type>Conference Paper/Proceeding/Abstract</type><journal>British Machine Vision Conference</journal><publisher/><keywords>Convolutional Neural Network, Deep Learning, Machine Learning, Graph CNN</keywords><publishedDay>30</publishedDay><publishedMonth>9</publishedMonth><publishedYear>2016</publishedYear><publishedDate>2016-09-30</publishedDate><doi/><url/><notes/><college>COLLEGE NANME</college><department>Computer Science</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>SCS</DepartmentCode><institution>Swansea University</institution><apcterm/><lastEdited>2017-03-23T12:27:29.0917621</lastEdited><Created>2017-02-24T23:30:27.8601763</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Mike</firstname><surname>Edwards</surname><order>1</order></author><author><firstname>Xianghua</firstname><surname>Xie</surname><orcid>0000-0002-2701-8660</orcid><order>2</order></author></authors><documents><document><filename>0032103-24022017233147.pdf</filename><originalFilename>bmvc2016.pdf</originalFilename><uploaded>2017-02-24T23:31:47.9070000</uploaded><type>Output</type><contentLength>2266155</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><embargoDate>2017-02-24T00:00:00.0000000</embargoDate><copyrightCorrect>true</copyrightCorrect><language>eng</language></document></documents><OutputDurs/></rfc1807>
spelling 2017-03-23T12:27:29.0917621 v2 32103 2017-02-24 Graph Convolutional Neural Network b334d40963c7a2f435f06d2c26c74e11 0000-0002-2701-8660 Xianghua Xie Xianghua Xie true false 2017-02-24 SCS The benefit of localized features within the regular domain has given rise to the use of Convolutional Neural Networks (CNNs) in machine learning, with great proficiency in the image classification. The use of CNNs becomes problematic within the irregular spatial domain due to design and convolution of a kernel filter being non-trivial. One so- lution to this problem is to utilize graph signal processing techniques and the convolution theorem to perform convolutions on the graph of the irregular domain to obtain feature map responses to learnt filters. We propose graph convolution and pooling operators analogous to those in the regular domain. We also provide gradient calculations on the input data and spectral filters, which allow for the deep learning of an irregular spatial do- main problem. Signal filters take the form of spectral multipliers, applying convolution in the graph spectral domain. Applying smooth multipliers results in localized convo- lutions in the spatial domain, with smoother multipliers providing sharper feature maps. Algebraic Multigrid is presented as a graph pooling method, reducing the resolution of the graph through agglomeration of nodes between layers of the network. Evaluation of performance on the MNIST digit classification problem in both the regular and irregu- lar domain is presented, with comparison drawn to standard CNN. The proposed graph CNN provides a deep learning method for the irregular domains present in the machine learning community, obtaining 94.23% on the regular grid, and 94.96% on a spatially irregular subsampled MNIST. Conference Paper/Proceeding/Abstract British Machine Vision Conference Convolutional Neural Network, Deep Learning, Machine Learning, Graph CNN 30 9 2016 2016-09-30 COLLEGE NANME Computer Science COLLEGE CODE SCS Swansea University 2017-03-23T12:27:29.0917621 2017-02-24T23:30:27.8601763 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Mike Edwards 1 Xianghua Xie 0000-0002-2701-8660 2 0032103-24022017233147.pdf bmvc2016.pdf 2017-02-24T23:31:47.9070000 Output 2266155 application/pdf Accepted Manuscript true 2017-02-24T00:00:00.0000000 true eng
title Graph Convolutional Neural Network
spellingShingle Graph Convolutional Neural Network
Xianghua Xie
title_short Graph Convolutional Neural Network
title_full Graph Convolutional Neural Network
title_fullStr Graph Convolutional Neural Network
title_full_unstemmed Graph Convolutional Neural Network
title_sort Graph Convolutional Neural Network
author_id_str_mv b334d40963c7a2f435f06d2c26c74e11
author_id_fullname_str_mv b334d40963c7a2f435f06d2c26c74e11_***_Xianghua Xie
author Xianghua Xie
author2 Mike Edwards
Xianghua Xie
format Conference Paper/Proceeding/Abstract
container_title British Machine Vision Conference
publishDate 2016
institution Swansea University
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
document_store_str 1
active_str 0
description The benefit of localized features within the regular domain has given rise to the use of Convolutional Neural Networks (CNNs) in machine learning, with great proficiency in the image classification. The use of CNNs becomes problematic within the irregular spatial domain due to design and convolution of a kernel filter being non-trivial. One so- lution to this problem is to utilize graph signal processing techniques and the convolution theorem to perform convolutions on the graph of the irregular domain to obtain feature map responses to learnt filters. We propose graph convolution and pooling operators analogous to those in the regular domain. We also provide gradient calculations on the input data and spectral filters, which allow for the deep learning of an irregular spatial do- main problem. Signal filters take the form of spectral multipliers, applying convolution in the graph spectral domain. Applying smooth multipliers results in localized convo- lutions in the spatial domain, with smoother multipliers providing sharper feature maps. Algebraic Multigrid is presented as a graph pooling method, reducing the resolution of the graph through agglomeration of nodes between layers of the network. Evaluation of performance on the MNIST digit classification problem in both the regular and irregu- lar domain is presented, with comparison drawn to standard CNN. The proposed graph CNN provides a deep learning method for the irregular domains present in the machine learning community, obtaining 94.23% on the regular grid, and 94.96% on a spatially irregular subsampled MNIST.
published_date 2016-09-30T03:39:17Z
_version_ 1763751763777683456
score 10.999252

Similar Items